Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12637
    Prev
    Next
    INDEX
    Explanations

    ville

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ležit
    -0.08
    (JSONObject
    -0.08
    kob
    -0.08
    lew
    -0.08
    ει
    -0.07
    (sel
    -0.07
     ולה
    -0.07
    तील
    -0.07
    _ATTRIBUTES
    -0.07
    (inter
    -0.07
    POSITIVE LOGITS
     masas
    0.07
     ausp
    0.07
     Chow
    0.07
     Calm
    0.07
     fluffy
    0.07
     Ur
    0.07
     حج
    0.07
    ublisher
    0.07
     Lawrence
    0.07
     승
    0.07
    Activations Density 0.111%

    No Known Activations